Professor Li of National Cheng Kung University, Taiwan

Graph structures can be used to describe various relationships and interactions among individuals, with graph data-based machine learning downstream tasks, including essential node classification and link prediction, belonging to the realm of Graph Machine Learning (GML). The advancement of deep learning techniques has enabled the effective learning of node feature representation vectors on graph data, known as Graph Representation Learning (GRL), and even training node feature generation and downstream tasks simultaneously, forming Graph Neural Networks (GNNs). In this keynote speech, we will introduce the most crucial GRL and GNN techniques in the field of graph machine learning and showcase the superior and extensive feature representation learning capabilities of GML through research achievements. We will demonstrate how graph machine learning can be gracefully integrated into various data types that do not have a pre-existing graph structure. This includes tabular data classification, regression, missing value processing, anomaly detection, and natural language processing tasks such as fake news detection and text classification. We will also explore time series prediction tasks and provide examples of how GNN can be applied to recommendation systems, computer vision, and drug development. Our goal is to help the audience understand and attempt to incorporate graph machine learning into their research fields and project tasks. Furthermore, we will examine how graph machine learning can be utilized in different scenarios, such as tabular data, natural language processing, and time series prediction. By providing various examples of GNN applications in recommendation systems, computer vision, and drug development, we hope to inspire the audience to consider the potential of graph machine learning in their own work. If time permits, we will also discuss the development direction of graph machine learning in the context of trustworthy artificial intelligence. By shedding light on the future of GML and its potential role in ensuring the trustworthiness of AI systems, we aim to provide a comprehensive outlook on the evolving landscape of graphbased learning techniques.

Biography:

Dr. Cheng-Te Li is currently Full Professor at the Department of Computer Science and Information Engineering, National Cheng Kung University (NCKU) in Tainan, Taiwan. He earned his Ph.D. degree in 2013 from the Graduate Institute of Networking and Multimedia at National Taiwan University. Prior to joining NCKU, Dr. Li served as an Assistant Research Fellow at CITI, Academia Sinica, from 2014 to 2016. Focusing on Machine Learning and Data Mining, Dr. Li's research explores their applications in Social Networks, Social Media, Recommender Systems, and Natural Language Processing. His work has been featured at premier conferences such as KDD, TheWebConf (WWW), ICDM, CIKM, SIGIR, IJCAI, ACL, EMNLP, and NAACL. Recently, his group has presented lecture-style tutorials on Graph Neural Networks at top conferences, including WWW, IEEE ICDE, and ACML. Dr. Li's academic achievements have been widely recognized, earning him important awards including the CIEE Outstanding Youth Electrical Engineer Award (2023), Y. Z. Hsu Scientific Paper Award (2022), FAOS Young Scholars' Creativity Award (2021), MOST Future Tech Awards (2023, 2021, 2020), TAAI Domestic Track Best Paper Award (2020), K. T. Li Young Researcher Award (2019), and MOST Young Scholar Fellowship (2018). Dr. Li leads the Networked Artificial Intelligence Laboratory (NetAI Lab) at NCKU.

Address:Taiwan